2 papers
cs.LG2025
Semi-gradient DICE for Offline Constrained Reinforcement Learning
Woosung Kim, JunHo Seo, Jongmin Lee +1
Stationary Distribution Correction Estimation (DICE) addresses the mismatch between the stationary distribution induced by a policy and the target distribution required for reliabl…
cs.LG2025
FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning
Woosung Kim, Jinho Lee, Jongmin Lee +1
Multi-objective reinforcement learning (MORL) aims to optimize policies in the presence of conflicting objectives, where linear scalarization is commonly used to reduce vector-valu…